<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Open-Source on Anshul Patel</title><link>http://www.anshulpatel.in/tags/open-source/</link><description>Recent content in Open-Source on Anshul Patel</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 04 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="http://www.anshulpatel.in/tags/open-source/index.xml" rel="self" type="application/rss+xml"/><item><title>Introducing DroidLlama: High-Performance Local LLM Hosting on Android</title><link>http://www.anshulpatel.in/posts/introducing_droidllama/</link><pubDate>Sat, 04 Jul 2026 00:00:00 +0000</pubDate><guid>http://www.anshulpatel.in/posts/introducing_droidllama/</guid><description>&lt;p&gt;If you are a self-hosting enthusiast or a homelab tinkerer, you likely have one
or two older Android smartphones gathering dust in a drawer. In my previous
posts, I’ve shared how these devices make
&lt;a href="../mobile_soc_for_homelab/" &gt;fantastic, cheap homelab hardware&lt;/a&gt; and how to
&lt;a href="../opensourcing_termux_api_exporter/" &gt;monitor them the Prometheus way&lt;/a&gt;. Today,
I want to take this mobile-first infrastructure setup to the next level.&lt;/p&gt;
&lt;p&gt;What if your smartphone could serve as a dedicated, local Large Language Model
(LLM) server for your automated home network?&lt;/p&gt;
&lt;p&gt;Meet &lt;strong&gt;DroidLlama&lt;/strong&gt;, a high-performance, long-running REST API server for
Android that implements the Ollama API specification. By wrapping a lightweight
model runner in a persistent Android service, DroidLlama allows any device on
your local network to use your smartphone as a private, local AI provider. 🚀&lt;/p&gt;</description></item></channel></rss>